Large Language Model-Based Feature Engineering

Latest papers

18 papers1 paper in the last four weeks, down 67% on the four weeks before. 0.0% of all new papers.

Long Text to Predictive Features: LLM-Guided Blockwise Feature Engineering via Executable Program Search
Oct 8, 2026Ziming Dai, Dabiao Ma, Ziheng Guo +2Automated Feature Engineering Large Language Model-Based Feature Engineering
City University of Hong Kong Hong Kong, China
LLMs as Feature Engineers for Text-and-Tabular Prediction
Sep 18, 2026Merwan Barlier, Blaz SkrljAutomated Feature Engineering Large Language Model-Based Feature Engineering
Teads
LLM-Generated Feature Pools for Time Series Anomaly Detection
Sep 18, 2026Youssef Attia El Hili, Malik Tiomoko, Corinne AncourtLarge Language Model-Based Feature Engineering Time-Series Anomaly Detection
Huawei Noah’s Ark Lab, Paris, France · Centre de Recherche en Informatique, Mines Paris, PSL University
SymboLLM-FE: LLM-Accelerated Symbolic Regression for Automated Feature Engineering on Tabular Data
Aug 28, 2026Zi-Jian Cheng, Zi-Yi Jia, Zhi Zhou +2Large Language Model-Based Feature Engineering Automated Feature Engineering
National Key Laboratory for Novel Software Technology, Nanjing University · School of Intelligence Science and Technology, Nanjing University · School of Artificial Intelligence, Nanjing University
SIGMA: SHAP-Guided Implicit-Trajectory Generation for Metadata-Free LLM-Based AutoFE
Aug 18, 2026Xuan Zheng, Kento Uchida, Shinichi ShirakawaLarge Language Model-Based Feature Engineering Automated Feature Engineering
Yokohama National University
Synthesizing Feature Extractors: An Agentic Approach for Algorithm Selection
Aug 17, 2026Hai Xia, Carlos Ansótegui, Stefan SzeiderAlgorithm Selection Automated Feature Engineering
Algorithms and Complexity Group, TU Wien, Vienna, Austria · Logic & Optimization Group, University of Lleida, Lleida, Spain
Adaptive Graph-of-Islands Evolution for Automatic Feature Engineering with LLMs
Jul 25, 2026Sha Li, Naren RamakrishnanEvolutionary Optimization Large Language Model-Guided Optimization
Department of Computer Science Virginia Tech Blacksburg, VA 24060 · Department of Computer Science Virginia Tech Alexandria, VA 22305
Evolutionary Feature Engineering for Structured Data
Jul 2, 2026Ege Onur Taga, Yilin Zhuang, M. Emrullah Ildiz +4Large Language Model-Guided Optimization Time Series Forecasting
University of Michigan · Google Research
When LLMs Analyze Scars: From Images to Clinically-Meaningful Features
Jun 16, 2026Ruman Wang, Hangting YeMedical Diagnosis Medical Image Classification
Liaoning University of Traditional Chinese Medicine · School of Artificial Intelligence, Jilin University
Eureka: Intelligent Feature Engineering for Enterprise AI Cloud Resource Demand Prediction
May 24, 2026Hangxuan Li, Renjun Jia, Xuezhang Wu +3LLM-Based Program Synthesis Cloud Computing
Alibaba Cloud Computing Co. Ltd, Hangzhou, China · School of Computer Science, Fudan University, Shanghai, China · School of Computer Science and Technology, Tongji University, Shanghai, China +1
FeatEHR-LLM: Leveraging Large Language Models for Feature Engineering in Electronic Health Records
Apr 24, 2026Hojjat Karami, David Atienza, Jean-Philippe Thiran +1Healthcare Electronic Health Records
1École Polytechnique Fédérale de Lausanne (EPFL), Lausanne, Switzerland
CoFEE: Reasoning Control for LLM-Based Feature Discovery
Apr 23, 2026Maximilian Westermann, Ben Griffin, Aaron Ontoyin Yin +6LLM Prompting Automated Feature Engineering
University of Oxford · Vela Research · Amazon
Memory-Augmented LLM-based Multi-Agent System for Automated Feature Generation on Tabular Data
Apr 22, 2026Fengxian Dong, Zhi Zheng, Xiao Han +5Tabular ML Multi-Agent LLMs
University of Science and Technology of China · Zhejiang University of Technology · Meituan
Embedding-Aware Feature Discovery: Bridging Latent Representations and Interpretable Features in Event Sequences
Mar 16, 2026Artem Sakhno, Ivan Sergeev, Alexey Shestov +5Large Language Model-Based Feature Engineering Automated Feature Engineering
Sber AI Lab · ISP RAS Research Center for Trusted AI
LLMs can construct powerful representations and streamline sample-efficient supervised learning
Mar 12, 2026Ilker Demirel, Lawrence Shi, Zeshan Hussain +1Large Language Model-Based Feature Engineering Data-Efficient Learning
MIT · Harvard Medical School
FAMOSE: A ReAct Approach to Automated Feature Discovery
Feb 19, 2026Keith Burghardt, Jienan Liu, Sadman Sakib +2Automated Feature Engineering Large Language Model-Based Feature Engineering
Amazon.com, Inc., 410 Terry Ave N, Seattle, WA 98109, United States.
MedFeat: Model-Aware and Explainability-Driven Feature Engineering with LLMs for Tabular Prediction
Feb 10, 2026Zizheng Zhang, Yiming Li, Justin Xu +6Interpretable ML Clinical Prediction
Microsoft Research · University of Oxford
DeepFeature: LLM-Empowered Context-aware Feature Generation for Wearable Biosignals
Dec 9, 2025Kaiwei Liu, Yuting He, Bufang Yang +6Wearable Sensing Wearable Health Monitoring
The Chinese University of Hong Kong, China · The Education University of Hong Kong, China · Hong Kong Applied Science and Technology Research Institute, China +1

Oct 8, 2026J/K move · Enter open · S save

Long Text to Predictive Features: LLM-Guided Blockwise Feature Engineering via Executable Program Search

Ziming Dai, Dabiao Ma, Ziheng Guo, Jack Dong+1

City University of Hong Kong Hong Kong, China

Automated Feature Engineering Large Language Model-Based Feature Engineering Large Language Model-Guided Optimization Program Synthesis

Open paper AskPDF arXiv

Industrial risk-control systems typically rely on structured-data models for efficient prediction, yet substantial valuable information remains embedded in unstructured long text. Extracting this information through manual feature engineering is labor-intensive, while requiring a large language model (LLM) to process every real-time input may not meet practical deployment requirements. To address this challenge, we propose LLM-BlockFE, an LLM-guided offline feature construction framework that converts long text into executable feature programs, thereby avoiding LLM calls during online inference. LLM-BlockFE constructs feature programs by incrementally appending immutable code blocks and evaluates candidate features using a downstream model. To address the tendency of conventional greedy search to become trapped in suboptimal solutions, our method introduces a block-level rollback mechanism based on depth-calibrated credit allocation and advances multiple independent search trajectories in an interleaved manner, reducing redundant exploration by sharing fixed descriptions of each trajectory's exploration direction. After the search, the resulting programs are frozen and deployed to extract structured features for downstream prediction models. Across two public and two private datasets, LLM-BlockFE achieves absolute AUC improvements of 0.0069 to 0.0358 over the strongest baseline on each dataset in the full-dataset comparison. Post-launch monitoring across five deployed financial risk-control applications shows absolute KS improvements of 0.02 to 1.56 percentage points over the existing manually designed strategy.